{"url":"/dataset/vd-ref","name":"VD-Ref","full_name":null,"description_markdown":"**VD-Ref** is a dataset with ground-truth mappings from both noun phrases and pronouns to image regions. This dataset contains a set of 10k complete sets from the VisDialog dataset, and uses the StanfordCoreNLP tool to tokenize the sentences, making it proper for the succeeding human annotation.\r\n\r\nSource: [Extending Phrase Grounding with Pronouns in Visual Dialogues](https://arxiv.org/pdf/2210.12658v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.12658v1.pdf](https://arxiv.org/pdf/2210.12658v1.pdf)","description_withheld":null,"homepage":"https://github.com/izhx/Phrase-Grounding-with-Pronoun","introduced_date":"2022-10-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/extending-phrase-grounding-with-pronouns-in","title":"Extending Phrase Grounding with Pronouns in Visual Dialogues","first_author":"Panzhong Lu","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Phrase Grounding","url":"/task/phrase-grounding","datasets_with_task":"/datasets/task/phrase-grounding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VD-Ref"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}